Hugging Face's logo

wangrongsheng
/
Baichuan-13B-Chat-sft-multi

PEFT
Model card Files Community
wangrongsheng commited on
Commit
ba7e7ef
•
1 Parent(s): 2b3090e

commit from root

Browse files
Files changed (21) hide show
  1. README.md +20 -0
  2. adapter_config.json +20 -0
  3. adapter_model.bin +3 -0
  4. all_results.json +7 -0
  5. checkpoint-1000/README.md +20 -0
  6. checkpoint-1000/adapter_config.json +20 -0
  7. checkpoint-1000/adapter_model.bin +3 -0
  8. checkpoint-1000/finetuning_args.json +12 -0
  9. checkpoint-1000/optimizer.pt +3 -0
  10. checkpoint-1000/rng_state_0.pth +3 -0
  11. checkpoint-1000/rng_state_1.pth +3 -0
  12. checkpoint-1000/rng_state_2.pth +3 -0
  13. checkpoint-1000/scheduler.pt +3 -0
  14. checkpoint-1000/trainer_state.json +616 -0
  15. checkpoint-1000/training_args.bin +3 -0
  16. finetuning_args.json +12 -0
  17. train_results.json +7 -0
  18. trainer_log.jsonl +144 -0
  19. trainer_state.json +883 -0
  20. training_args.bin +3 -0
  21. training_loss.png +0 -0
README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: True
16
+ - bnb_4bit_compute_dtype: float16
17
+ ### Framework versions
18
+
19
+
20
+ - PEFT 0.4.0
adapter_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "../Baichuan-13B-Chat",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 32.0,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "W_pack"
18
+ ],
19
+ "task_type": "CAUSAL_LM"
20
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:347ed74646f3d3062936975c83322b755da3be5b0aac3e172433075fed5c9492
3
+ size 26241825
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "train_loss": 1.285984360292989,
4
+ "train_runtime": 22790.2039,
5
+ "train_samples_per_second": 6.057,
6
+ "train_steps_per_second": 0.063
7
+ }
checkpoint-1000/README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: True
16
+ - bnb_4bit_compute_dtype: float16
17
+ ### Framework versions
18
+
19
+
20
+ - PEFT 0.4.0
checkpoint-1000/adapter_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "../Baichuan-13B-Chat",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 32.0,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "W_pack"
18
+ ],
19
+ "task_type": "CAUSAL_LM"
20
+ }
checkpoint-1000/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:363e7a9f2c3bf391b446b3ff0671060a0b07ad189508c5ffa97089d2016fe55b
3
+ size 26241825
checkpoint-1000/finetuning_args.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "finetuning_type": "lora",
3
+ "lora_alpha": 32.0,
4
+ "lora_dropout": 0.1,
5
+ "lora_rank": 8,
6
+ "lora_target": [
7
+ "W_pack"
8
+ ],
9
+ "name_module_trainable": "mlp",
10
+ "num_hidden_layers": 32,
11
+ "num_layer_trainable": 3
12
+ }
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ffbd8b2f5d257fe4e9e9d4a4a417f9f19e362f79e9d2fb6a957e0c4b0d2875a
3
+ size 52496005
checkpoint-1000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:371d3f4a66be4a6fc2006d0eb15e416833d1915331e003e1eb0a965733032b66
3
+ size 18679
checkpoint-1000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01d22ab5112df9cda52b1b2513114f4141603fad9db89465dfe16698e4abcf72
3
+ size 18679
checkpoint-1000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdbd2fe7f0af8978f7adaecb0af07768a8c08a964da6c411980e284b82af554a
3
+ size 18679
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:422f34a10b24ba08dd2630b19f2c878735a17e26283fdf0109446f080aa5b0c8
3
+ size 627
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,616 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.3908205841446453,
5
+ "global_step": 1000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 4.999403411726636e-05,
13
+ "loss": 1.8493,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.03,
18
+ "learning_rate": 4.997613931640598e-05,
19
+ "loss": 1.613,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.04,
24
+ "learning_rate": 4.9946324138081534e-05,
25
+ "loss": 1.5193,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.06,
30
+ "learning_rate": 4.990460281220164e-05,
31
+ "loss": 1.4805,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.07,
36
+ "learning_rate": 4.98509952511293e-05,
37
+ "loss": 1.443,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.08,
42
+ "learning_rate": 4.978552704017835e-05,
43
+ "loss": 1.4186,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.1,
48
+ "learning_rate": 4.9708229425402354e-05,
49
+ "loss": 1.394,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.11,
54
+ "learning_rate": 4.961913929868172e-05,
55
+ "loss": 1.38,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.13,
60
+ "learning_rate": 4.9518299180116366e-05,
61
+ "loss": 1.3715,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.14,
66
+ "learning_rate": 4.940575719773205e-05,
67
+ "loss": 1.3548,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.15,
72
+ "learning_rate": 4.928156706451035e-05,
73
+ "loss": 1.3536,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.17,
78
+ "learning_rate": 4.9145788052752975e-05,
79
+ "loss": 1.3535,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.18,
84
+ "learning_rate": 4.899848496579287e-05,
85
+ "loss": 1.3414,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.19,
90
+ "learning_rate": 4.883972810706548e-05,
91
+ "loss": 1.3275,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.21,
96
+ "learning_rate": 4.866959324655501e-05,
97
+ "loss": 1.3342,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.22,
102
+ "learning_rate": 4.8488161584631574e-05,
103
+ "loss": 1.3234,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.24,
108
+ "learning_rate": 4.829551971329672e-05,
109
+ "loss": 1.3235,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 0.25,
114
+ "learning_rate": 4.809175957485558e-05,
115
+ "loss": 1.3245,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 0.26,
120
+ "learning_rate": 4.7876978418035455e-05,
121
+ "loss": 1.3132,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 0.28,
126
+ "learning_rate": 4.7651278751571984e-05,
127
+ "loss": 1.3193,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 0.29,
132
+ "learning_rate": 4.7414768295284594e-05,
133
+ "loss": 1.3158,
134
+ "step": 210
135
+ },
136
+ {
137
+ "epoch": 0.31,
138
+ "learning_rate": 4.716755992866509e-05,
139
+ "loss": 1.3089,
140
+ "step": 220
141
+ },
142
+ {
143
+ "epoch": 0.32,
144
+ "learning_rate": 4.6909771637003556e-05,
145
+ "loss": 1.3232,
146
+ "step": 230
147
+ },
148
+ {
149
+ "epoch": 0.33,
150
+ "learning_rate": 4.664152645507744e-05,
151
+ "loss": 1.307,
152
+ "step": 240
153
+ },
154
+ {
155
+ "epoch": 0.35,
156
+ "learning_rate": 4.636295240843068e-05,
157
+ "loss": 1.3057,
158
+ "step": 250
159
+ },
160
+ {
161
+ "epoch": 0.36,
162
+ "learning_rate": 4.607418245227089e-05,
163
+ "loss": 1.2985,
164
+ "step": 260
165
+ },
166
+ {
167
+ "epoch": 0.38,
168
+ "learning_rate": 4.577535440801368e-05,
169
+ "loss": 1.3111,
170
+ "step": 270
171
+ },
172
+ {
173
+ "epoch": 0.39,
174
+ "learning_rate": 4.546661089750462e-05,
175
+ "loss": 1.2948,
176
+ "step": 280
177
+ },
178
+ {
179
+ "epoch": 0.4,
180
+ "learning_rate": 4.5148099274950005e-05,
181
+ "loss": 1.3037,
182
+ "step": 290
183
+ },
184
+ {
185
+ "epoch": 0.42,
186
+ "learning_rate": 4.481997155658898e-05,
187
+ "loss": 1.3042,
188
+ "step": 300
189
+ },
190
+ {
191
+ "epoch": 0.43,
192
+ "learning_rate": 4.4482384348140695e-05,
193
+ "loss": 1.2899,
194
+ "step": 310
195
+ },
196
+ {
197
+ "epoch": 0.45,
198
+ "learning_rate": 4.413549877006099e-05,
199
+ "loss": 1.3006,
200
+ "step": 320
201
+ },
202
+ {
203
+ "epoch": 0.46,
204
+ "learning_rate": 4.3779480380644337e-05,
205
+ "loss": 1.2908,
206
+ "step": 330
207
+ },
208
+ {
209
+ "epoch": 0.47,
210
+ "learning_rate": 4.34144990970077e-05,
211
+ "loss": 1.2898,
212
+ "step": 340
213
+ },
214
+ {
215
+ "epoch": 0.49,
216
+ "learning_rate": 4.304072911399415e-05,
217
+ "loss": 1.2822,
218
+ "step": 350
219
+ },
220
+ {
221
+ "epoch": 0.5,
222
+ "learning_rate": 4.2658348821034724e-05,
223
+ "loss": 1.2927,
224
+ "step": 360
225
+ },
226
+ {
227
+ "epoch": 0.51,
228
+ "learning_rate": 4.226754071700841e-05,
229
+ "loss": 1.2847,
230
+ "step": 370
231
+ },
232
+ {
233
+ "epoch": 0.53,
234
+ "learning_rate": 4.1868491323140816e-05,
235
+ "loss": 1.2873,
236
+ "step": 380
237
+ },
238
+ {
239
+ "epoch": 0.54,
240
+ "learning_rate": 4.146139109398303e-05,
241
+ "loss": 1.288,
242
+ "step": 390
243
+ },
244
+ {
245
+ "epoch": 0.56,
246
+ "learning_rate": 4.1046434326513305e-05,
247
+ "loss": 1.2849,
248
+ "step": 400
249
+ },
250
+ {
251
+ "epoch": 0.57,
252
+ "learning_rate": 4.062381906740477e-05,
253
+ "loss": 1.2819,
254
+ "step": 410
255
+ },
256
+ {
257
+ "epoch": 0.58,
258
+ "learning_rate": 4.019374701850362e-05,
259
+ "loss": 1.2694,
260
+ "step": 420
261
+ },
262
+ {
263
+ "epoch": 0.6,
264
+ "learning_rate": 3.975642344056271e-05,
265
+ "loss": 1.2843,
266
+ "step": 430
267
+ },
268
+ {
269
+ "epoch": 0.61,
270
+ "learning_rate": 3.931205705527664e-05,
271
+ "loss": 1.2646,
272
+ "step": 440
273
+ },
274
+ {
275
+ "epoch": 0.63,
276
+ "learning_rate": 3.886085994566506e-05,
277
+ "loss": 1.277,
278
+ "step": 450
279
+ },
280
+ {
281
+ "epoch": 0.64,
282
+ "learning_rate": 3.840304745485162e-05,
283
+ "loss": 1.2769,
284
+ "step": 460
285
+ },
286
+ {
287
+ "epoch": 0.65,
288
+ "learning_rate": 3.7938838083287056e-05,
289
+ "loss": 1.2797,
290
+ "step": 470
291
+ },
292
+ {
293
+ "epoch": 0.67,
294
+ "learning_rate": 3.746845338446533e-05,
295
+ "loss": 1.2776,
296
+ "step": 480
297
+ },
298
+ {
299
+ "epoch": 0.68,
300
+ "learning_rate": 3.6992117859182674e-05,
301
+ "loss": 1.2847,
302
+ "step": 490
303
+ },
304
+ {
305
+ "epoch": 0.7,
306
+ "learning_rate": 3.651005884838995e-05,
307
+ "loss": 1.2762,
308
+ "step": 500
309
+ },
310
+ {
311
+ "epoch": 0.71,
312
+ "learning_rate": 3.6022506424689485e-05,
313
+ "loss": 1.2834,
314
+ "step": 510
315
+ },
316
+ {
317
+ "epoch": 0.72,
318
+ "learning_rate": 3.552969328252817e-05,
319
+ "loss": 1.2754,
320
+ "step": 520
321
+ },
322
+ {
323
+ "epoch": 0.74,
324
+ "learning_rate": 3.5031854627139284e-05,
325
+ "loss": 1.2807,
326
+ "step": 530
327
+ },
328
+ {
329
+ "epoch": 0.75,
330
+ "learning_rate": 3.452922806228587e-05,
331
+ "loss": 1.2783,
332
+ "step": 540
333
+ },
334
+ {
335
+ "epoch": 0.76,
336
+ "learning_rate": 3.402205347685953e-05,
337
+ "loss": 1.2748,
338
+ "step": 550
339
+ },
340
+ {
341
+ "epoch": 0.78,
342
+ "learning_rate": 3.351057293038841e-05,
343
+ "loss": 1.2737,
344
+ "step": 560
345
+ },
346
+ {
347
+ "epoch": 0.79,
348
+ "learning_rate": 3.2995030537509396e-05,
349
+ "loss": 1.2729,
350
+ "step": 570
351
+ },
352
+ {
353
+ "epoch": 0.81,
354
+ "learning_rate": 3.247567235145929e-05,
355
+ "loss": 1.2712,
356
+ "step": 580
357
+ },
358
+ {
359
+ "epoch": 0.82,
360
+ "learning_rate": 3.195274624664086e-05,
361
+ "loss": 1.2716,
362
+ "step": 590
363
+ },
364
+ {
365
+ "epoch": 0.83,
366
+ "learning_rate": 3.14265018003197e-05,
367
+ "loss": 1.2823,
368
+ "step": 600
369
+ },
370
+ {
371
+ "epoch": 0.85,
372
+ "learning_rate": 3.089719017350828e-05,
373
+ "loss": 1.2627,
374
+ "step": 610
375
+ },
376
+ {
377
+ "epoch": 0.86,
378
+ "learning_rate": 3.03650639910942e-05,
379
+ "loss": 1.2658,
380
+ "step": 620
381
+ },
382
+ {
383
+ "epoch": 0.88,
384
+ "learning_rate": 2.983037722126978e-05,
385
+ "loss": 1.2803,
386
+ "step": 630
387
+ },
388
+ {
389
+ "epoch": 0.89,
390
+ "learning_rate": 2.929338505432045e-05,
391
+ "loss": 1.2731,
392
+ "step": 640
393
+ },
394
+ {
395
+ "epoch": 0.9,
396
+ "learning_rate": 2.8754343780829968e-05,
397
+ "loss": 1.2652,
398
+ "step": 650
399
+ },
400
+ {
401
+ "epoch": 0.92,
402
+ "learning_rate": 2.821351066936043e-05,
403
+ "loss": 1.2717,
404
+ "step": 660
405
+ },
406
+ {
407
+ "epoch": 0.93,
408
+ "learning_rate": 2.767114384366555e-05,
409
+ "loss": 1.259,
410
+ "step": 670
411
+ },
412
+ {
413
+ "epoch": 0.95,
414
+ "learning_rate": 2.7127502159495782e-05,
415
+ "loss": 1.2753,
416
+ "step": 680
417
+ },
418
+ {
419
+ "epoch": 0.96,
420
+ "learning_rate": 2.6582845081054096e-05,
421
+ "loss": 1.2744,
422
+ "step": 690
423
+ },
424
+ {
425
+ "epoch": 0.97,
426
+ "learning_rate": 2.6037432557161285e-05,
427
+ "loss": 1.2634,
428
+ "step": 700
429
+ },
430
+ {
431
+ "epoch": 0.99,
432
+ "learning_rate": 2.5491524897190068e-05,
433
+ "loss": 1.2668,
434
+ "step": 710
435
+ },
436
+ {
437
+ "epoch": 1.0,
438
+ "learning_rate": 2.4945382646827058e-05,
439
+ "loss": 1.2642,
440
+ "step": 720
441
+ },
442
+ {
443
+ "epoch": 1.02,
444
+ "learning_rate": 2.4399266463721993e-05,
445
+ "loss": 1.2636,
446
+ "step": 730
447
+ },
448
+ {
449
+ "epoch": 1.03,
450
+ "learning_rate": 2.3853436993083453e-05,
451
+ "loss": 1.269,
452
+ "step": 740
453
+ },
454
+ {
455
+ "epoch": 1.04,
456
+ "learning_rate": 2.3308154743280595e-05,
457
+ "loss": 1.2489,
458
+ "step": 750
459
+ },
460
+ {
461
+ "epoch": 1.06,
462
+ "learning_rate": 2.2763679961510137e-05,
463
+ "loss": 1.2586,
464
+ "step": 760
465
+ },
466
+ {
467
+ "epoch": 1.07,
468
+ "learning_rate": 2.222027250958805e-05,
469
+ "loss": 1.2633,
470
+ "step": 770
471
+ },
472
+ {
473
+ "epoch": 1.08,
474
+ "learning_rate": 2.1678191739925107e-05,
475
+ "loss": 1.2576,
476
+ "step": 780
477
+ },
478
+ {
479
+ "epoch": 1.1,
480
+ "learning_rate": 2.1137696371745608e-05,
481
+ "loss": 1.259,
482
+ "step": 790
483
+ },
484
+ {
485
+ "epoch": 1.11,
486
+ "learning_rate": 2.059904436760835e-05,
487
+ "loss": 1.2697,
488
+ "step": 800
489
+ },
490
+ {
491
+ "epoch": 1.13,
492
+ "learning_rate": 2.006249281028859e-05,
493
+ "loss": 1.2505,
494
+ "step": 810
495
+ },
496
+ {
497
+ "epoch": 1.14,
498
+ "learning_rate": 1.9528297780080067e-05,
499
+ "loss": 1.2651,
500
+ "step": 820
501
+ },
502
+ {
503
+ "epoch": 1.15,
504
+ "learning_rate": 1.899671423257534e-05,
505
+ "loss": 1.2569,
506
+ "step": 830
507
+ },
508
+ {
509
+ "epoch": 1.17,
510
+ "learning_rate": 1.8467995876983002e-05,
511
+ "loss": 1.2617,
512
+ "step": 840
513
+ },
514
+ {
515
+ "epoch": 1.18,
516
+ "learning_rate": 1.7942395055039756e-05,
517
+ "loss": 1.2501,
518
+ "step": 850
519
+ },
520
+ {
521
+ "epoch": 1.2,
522
+ "learning_rate": 1.742016262057507e-05,
523
+ "loss": 1.2575,
524
+ "step": 860
525
+ },
526
+ {
527
+ "epoch": 1.21,
528
+ "learning_rate": 1.690154781978604e-05,
529
+ "loss": 1.2583,
530
+ "step": 870
531
+ },
532
+ {
533
+ "epoch": 1.22,
534
+ "learning_rate": 1.638679817227951e-05,
535
+ "loss": 1.2671,
536
+ "step": 880
537
+ },
538
+ {
539
+ "epoch": 1.24,
540
+ "learning_rate": 1.5876159352938202e-05,
541
+ "loss": 1.2547,
542
+ "step": 890
543
+ },
544
+ {
545
+ "epoch": 1.25,
546
+ "learning_rate": 1.5369875074667365e-05,
547
+ "loss": 1.2585,
548
+ "step": 900
549
+ },
550
+ {
551
+ "epoch": 1.27,
552
+ "learning_rate": 1.4868186972077708e-05,
553
+ "loss": 1.2496,
554
+ "step": 910
555
+ },
556
+ {
557
+ "epoch": 1.28,
558
+ "learning_rate": 1.4371334486160354e-05,
559
+ "loss": 1.2524,
560
+ "step": 920
561
+ },
562
+ {
563
+ "epoch": 1.29,
564
+ "learning_rate": 1.3879554750008653e-05,
565
+ "loss": 1.2605,
566
+ "step": 930
567
+ },
568
+ {
569
+ "epoch": 1.31,
570
+ "learning_rate": 1.3393082475641544e-05,
571
+ "loss": 1.247,
572
+ "step": 940
573
+ },
574
+ {
575
+ "epoch": 1.32,
576
+ "learning_rate": 1.2912149841982388e-05,
577
+ "loss": 1.2629,
578
+ "step": 950
579
+ },
580
+ {
581
+ "epoch": 1.34,
582
+ "learning_rate": 1.2436986384046786e-05,
583
+ "loss": 1.2493,
584
+ "step": 960
585
+ },
586
+ {
587
+ "epoch": 1.35,
588
+ "learning_rate": 1.1967818883392306e-05,
589
+ "loss": 1.2556,
590
+ "step": 970
591
+ },
592
+ {
593
+ "epoch": 1.36,
594
+ "learning_rate": 1.150487125988224e-05,
595
+ "loss": 1.2531,
596
+ "step": 980
597
+ },
598
+ {
599
+ "epoch": 1.38,
600
+ "learning_rate": 1.1048364464815297e-05,
601
+ "loss": 1.2549,
602
+ "step": 990
603
+ },
604
+ {
605
+ "epoch": 1.39,
606
+ "learning_rate": 1.0598516375471978e-05,
607
+ "loss": 1.2554,
608
+ "step": 1000
609
+ }
610
+ ],
611
+ "max_steps": 1438,
612
+ "num_train_epochs": 2,
613
+ "total_flos": 2.19673855199386e+18,
614
+ "trial_name": null,
615
+ "trial_params": null
616
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50e1ef6c01b86ac38d5b495482e7d846564796979962b6b17f1f136a64b951a3
3
+ size 3286
finetuning_args.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "finetuning_type": "lora",
3
+ "lora_alpha": 32.0,
4
+ "lora_dropout": 0.1,
5
+ "lora_rank": 8,
6
+ "lora_target": [
7
+ "W_pack"
8
+ ],
9
+ "name_module_trainable": "mlp",
10
+ "num_hidden_layers": 32,
11
+ "num_layer_trainable": 3
12
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "train_loss": 1.285984360292989,
4
+ "train_runtime": 22790.2039,
5
+ "train_samples_per_second": 6.057,
6
+ "train_steps_per_second": 0.063
7
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 1438, "loss": 1.8493, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.999403411726636e-05, "epoch": 0.01, "percentage": 0.7, "elapsed_time": "0:02:37", "remaining_time": "6:15:54"}
2
+ {"current_steps": 20, "total_steps": 1438, "loss": 1.613, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.997613931640598e-05, "epoch": 0.03, "percentage": 1.39, "elapsed_time": "0:05:15", "remaining_time": "6:13:14"}
3
+ {"current_steps": 30, "total_steps": 1438, "loss": 1.5193, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9946324138081534e-05, "epoch": 0.04, "percentage": 2.09, "elapsed_time": "0:07:52", "remaining_time": "6:09:27"}
4
+ {"current_steps": 40, "total_steps": 1438, "loss": 1.4805, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.990460281220164e-05, "epoch": 0.06, "percentage": 2.78, "elapsed_time": "0:10:30", "remaining_time": "6:07:15"}
5
+ {"current_steps": 50, "total_steps": 1438, "loss": 1.443, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.98509952511293e-05, "epoch": 0.07, "percentage": 3.48, "elapsed_time": "0:13:06", "remaining_time": "6:03:57"}
6
+ {"current_steps": 60, "total_steps": 1438, "loss": 1.4186, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.978552704017835e-05, "epoch": 0.08, "percentage": 4.17, "elapsed_time": "0:15:40", "remaining_time": "5:59:51"}
7
+ {"current_steps": 70, "total_steps": 1438, "loss": 1.394, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9708229425402354e-05, "epoch": 0.1, "percentage": 4.87, "elapsed_time": "0:18:18", "remaining_time": "5:57:43"}
8
+ {"current_steps": 80, "total_steps": 1438, "loss": 1.38, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.961913929868172e-05, "epoch": 0.11, "percentage": 5.56, "elapsed_time": "0:20:58", "remaining_time": "5:56:09"}
9
+ {"current_steps": 90, "total_steps": 1438, "loss": 1.3715, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9518299180116366e-05, "epoch": 0.13, "percentage": 6.26, "elapsed_time": "0:23:36", "remaining_time": "5:53:41"}
10
+ {"current_steps": 100, "total_steps": 1438, "loss": 1.3548, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.940575719773205e-05, "epoch": 0.14, "percentage": 6.95, "elapsed_time": "0:26:17", "remaining_time": "5:51:46"}
11
+ {"current_steps": 110, "total_steps": 1438, "loss": 1.3536, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.928156706451035e-05, "epoch": 0.15, "percentage": 7.65, "elapsed_time": "0:28:58", "remaining_time": "5:49:43"}
12
+ {"current_steps": 120, "total_steps": 1438, "loss": 1.3535, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9145788052752975e-05, "epoch": 0.17, "percentage": 8.34, "elapsed_time": "0:31:32", "remaining_time": "5:46:23"}
13
+ {"current_steps": 130, "total_steps": 1438, "loss": 1.3414, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.899848496579287e-05, "epoch": 0.18, "percentage": 9.04, "elapsed_time": "0:34:05", "remaining_time": "5:42:57"}
14
+ {"current_steps": 140, "total_steps": 1438, "loss": 1.3275, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.883972810706548e-05, "epoch": 0.19, "percentage": 9.74, "elapsed_time": "0:36:41", "remaining_time": "5:40:09"}
15
+ {"current_steps": 150, "total_steps": 1438, "loss": 1.3342, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.866959324655501e-05, "epoch": 0.21, "percentage": 10.43, "elapsed_time": "0:39:18", "remaining_time": "5:37:28"}
16
+ {"current_steps": 160, "total_steps": 1438, "loss": 1.3234, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8488161584631574e-05, "epoch": 0.22, "percentage": 11.13, "elapsed_time": "0:41:51", "remaining_time": "5:34:20"}
17
+ {"current_steps": 170, "total_steps": 1438, "loss": 1.3235, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.829551971329672e-05, "epoch": 0.24, "percentage": 11.82, "elapsed_time": "0:44:27", "remaining_time": "5:31:38"}
18
+ {"current_steps": 180, "total_steps": 1438, "loss": 1.3245, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.809175957485558e-05, "epoch": 0.25, "percentage": 12.52, "elapsed_time": "0:47:03", "remaining_time": "5:28:56"}
19
+ {"current_steps": 190, "total_steps": 1438, "loss": 1.3132, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7876978418035455e-05, "epoch": 0.26, "percentage": 13.21, "elapsed_time": "0:49:41", "remaining_time": "5:26:24"}
20
+ {"current_steps": 200, "total_steps": 1438, "loss": 1.3193, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7651278751571984e-05, "epoch": 0.28, "percentage": 13.91, "elapsed_time": "0:52:21", "remaining_time": "5:24:02"}
21
+ {"current_steps": 210, "total_steps": 1438, "loss": 1.3158, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7414768295284594e-05, "epoch": 0.29, "percentage": 14.6, "elapsed_time": "0:55:01", "remaining_time": "5:21:44"}
22
+ {"current_steps": 220, "total_steps": 1438, "loss": 1.3089, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.716755992866509e-05, "epoch": 0.31, "percentage": 15.3, "elapsed_time": "0:57:35", "remaining_time": "5:18:51"}
23
+ {"current_steps": 230, "total_steps": 1438, "loss": 1.3232, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6909771637003556e-05, "epoch": 0.32, "percentage": 15.99, "elapsed_time": "1:00:14", "remaining_time": "5:16:24"}
24
+ {"current_steps": 240, "total_steps": 1438, "loss": 1.307, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.664152645507744e-05, "epoch": 0.33, "percentage": 16.69, "elapsed_time": "1:02:55", "remaining_time": "5:14:07"}
25
+ {"current_steps": 250, "total_steps": 1438, "loss": 1.3057, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.636295240843068e-05, "epoch": 0.35, "percentage": 17.39, "elapsed_time": "1:05:32", "remaining_time": "5:11:25"}
26
+ {"current_steps": 260, "total_steps": 1438, "loss": 1.2985, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.607418245227089e-05, "epoch": 0.36, "percentage": 18.08, "elapsed_time": "1:08:08", "remaining_time": "5:08:45"}
27
+ {"current_steps": 270, "total_steps": 1438, "loss": 1.3111, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.577535440801368e-05, "epoch": 0.38, "percentage": 18.78, "elapsed_time": "1:10:43", "remaining_time": "5:05:56"}
28
+ {"current_steps": 280, "total_steps": 1438, "loss": 1.2948, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.546661089750462e-05, "epoch": 0.39, "percentage": 19.47, "elapsed_time": "1:13:27", "remaining_time": "5:03:48"}
29
+ {"current_steps": 290, "total_steps": 1438, "loss": 1.3037, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5148099274950005e-05, "epoch": 0.4, "percentage": 20.17, "elapsed_time": "1:16:05", "remaining_time": "5:01:13"}
30
+ {"current_steps": 300, "total_steps": 1438, "loss": 1.3042, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.481997155658898e-05, "epoch": 0.42, "percentage": 20.86, "elapsed_time": "1:18:48", "remaining_time": "4:58:56"}
31
+ {"current_steps": 310, "total_steps": 1438, "loss": 1.2899, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.4482384348140695e-05, "epoch": 0.43, "percentage": 21.56, "elapsed_time": "1:21:29", "remaining_time": "4:56:31"}
32
+ {"current_steps": 320, "total_steps": 1438, "loss": 1.3006, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.413549877006099e-05, "epoch": 0.45, "percentage": 22.25, "elapsed_time": "1:24:16", "remaining_time": "4:54:27"}
33
+ {"current_steps": 330, "total_steps": 1438, "loss": 1.2908, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.3779480380644337e-05, "epoch": 0.46, "percentage": 22.95, "elapsed_time": "1:26:54", "remaining_time": "4:51:46"}
34
+ {"current_steps": 340, "total_steps": 1438, "loss": 1.2898, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.34144990970077e-05, "epoch": 0.47, "percentage": 23.64, "elapsed_time": "1:29:35", "remaining_time": "4:49:21"}
35
+ {"current_steps": 350, "total_steps": 1438, "loss": 1.2822, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.304072911399415e-05, "epoch": 0.49, "percentage": 24.34, "elapsed_time": "1:32:14", "remaining_time": "4:46:43"}
36
+ {"current_steps": 360, "total_steps": 1438, "loss": 1.2927, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.2658348821034724e-05, "epoch": 0.5, "percentage": 25.03, "elapsed_time": "1:34:53", "remaining_time": "4:44:08"}
37
+ {"current_steps": 370, "total_steps": 1438, "loss": 1.2847, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.226754071700841e-05, "epoch": 0.51, "percentage": 25.73, "elapsed_time": "1:37:36", "remaining_time": "4:41:43"}
38
+ {"current_steps": 380, "total_steps": 1438, "loss": 1.2873, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.1868491323140816e-05, "epoch": 0.53, "percentage": 26.43, "elapsed_time": "1:40:14", "remaining_time": "4:39:04"}
39
+ {"current_steps": 390, "total_steps": 1438, "loss": 1.288, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.146139109398303e-05, "epoch": 0.54, "percentage": 27.12, "elapsed_time": "1:42:50", "remaining_time": "4:36:21"}
40
+ {"current_steps": 400, "total_steps": 1438, "loss": 1.2849, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.1046434326513305e-05, "epoch": 0.56, "percentage": 27.82, "elapsed_time": "1:45:29", "remaining_time": "4:33:45"}
41
+ {"current_steps": 410, "total_steps": 1438, "loss": 1.2819, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.062381906740477e-05, "epoch": 0.57, "percentage": 28.51, "elapsed_time": "1:48:04", "remaining_time": "4:30:57"}
42
+ {"current_steps": 420, "total_steps": 1438, "loss": 1.2694, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.019374701850362e-05, "epoch": 0.58, "percentage": 29.21, "elapsed_time": "1:50:44", "remaining_time": "4:28:23"}
43
+ {"current_steps": 430, "total_steps": 1438, "loss": 1.2843, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.975642344056271e-05, "epoch": 0.6, "percentage": 29.9, "elapsed_time": "1:53:23", "remaining_time": "4:25:47"}
44
+ {"current_steps": 440, "total_steps": 1438, "loss": 1.2646, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.931205705527664e-05, "epoch": 0.61, "percentage": 30.6, "elapsed_time": "1:56:01", "remaining_time": "4:23:09"}
45
+ {"current_steps": 450, "total_steps": 1438, "loss": 1.277, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.886085994566506e-05, "epoch": 0.63, "percentage": 31.29, "elapsed_time": "1:58:39", "remaining_time": "4:20:31"}
46
+ {"current_steps": 460, "total_steps": 1438, "loss": 1.2769, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.840304745485162e-05, "epoch": 0.64, "percentage": 31.99, "elapsed_time": "2:01:15", "remaining_time": "4:17:49"}
47
+ {"current_steps": 470, "total_steps": 1438, "loss": 1.2797, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.7938838083287056e-05, "epoch": 0.65, "percentage": 32.68, "elapsed_time": "2:03:57", "remaining_time": "4:15:18"}
48
+ {"current_steps": 480, "total_steps": 1438, "loss": 1.2776, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.746845338446533e-05, "epoch": 0.67, "percentage": 33.38, "elapsed_time": "2:06:37", "remaining_time": "4:12:43"}
49
+ {"current_steps": 490, "total_steps": 1438, "loss": 1.2847, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6992117859182674e-05, "epoch": 0.68, "percentage": 34.08, "elapsed_time": "2:09:18", "remaining_time": "4:10:10"}
50
+ {"current_steps": 500, "total_steps": 1438, "loss": 1.2762, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.651005884838995e-05, "epoch": 0.7, "percentage": 34.77, "elapsed_time": "2:11:56", "remaining_time": "4:07:31"}
51
+ {"current_steps": 510, "total_steps": 1438, "loss": 1.2834, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6022506424689485e-05, "epoch": 0.71, "percentage": 35.47, "elapsed_time": "2:14:37", "remaining_time": "4:04:57"}
52
+ {"current_steps": 520, "total_steps": 1438, "loss": 1.2754, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.552969328252817e-05, "epoch": 0.72, "percentage": 36.16, "elapsed_time": "2:17:13", "remaining_time": "4:02:14"}
53
+ {"current_steps": 530, "total_steps": 1438, "loss": 1.2807, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.5031854627139284e-05, "epoch": 0.74, "percentage": 36.86, "elapsed_time": "2:19:47", "remaining_time": "3:59:29"}
54
+ {"current_steps": 540, "total_steps": 1438, "loss": 1.2783, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.452922806228587e-05, "epoch": 0.75, "percentage": 37.55, "elapsed_time": "2:22:34", "remaining_time": "3:57:05"}
55
+ {"current_steps": 550, "total_steps": 1438, "loss": 1.2748, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.402205347685953e-05, "epoch": 0.76, "percentage": 38.25, "elapsed_time": "2:25:09", "remaining_time": "3:54:21"}
56
+ {"current_steps": 560, "total_steps": 1438, "loss": 1.2737, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.351057293038841e-05, "epoch": 0.78, "percentage": 38.94, "elapsed_time": "2:27:47", "remaining_time": "3:51:42"}
57
+ {"current_steps": 570, "total_steps": 1438, "loss": 1.2729, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.2995030537509396e-05, "epoch": 0.79, "percentage": 39.64, "elapsed_time": "2:30:23", "remaining_time": "3:49:01"}
58
+ {"current_steps": 580, "total_steps": 1438, "loss": 1.2712, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.247567235145929e-05, "epoch": 0.81, "percentage": 40.33, "elapsed_time": "2:33:01", "remaining_time": "3:46:22"}
59
+ {"current_steps": 590, "total_steps": 1438, "loss": 1.2716, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.195274624664086e-05, "epoch": 0.82, "percentage": 41.03, "elapsed_time": "2:35:39", "remaining_time": "3:43:43"}
60
+ {"current_steps": 600, "total_steps": 1438, "loss": 1.2823, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.14265018003197e-05, "epoch": 0.83, "percentage": 41.72, "elapsed_time": "2:38:18", "remaining_time": "3:41:06"}
61
+ {"current_steps": 610, "total_steps": 1438, "loss": 1.2627, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.089719017350828e-05, "epoch": 0.85, "percentage": 42.42, "elapsed_time": "2:40:55", "remaining_time": "3:38:25"}
62
+ {"current_steps": 620, "total_steps": 1438, "loss": 1.2658, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.03650639910942e-05, "epoch": 0.86, "percentage": 43.12, "elapsed_time": "2:43:33", "remaining_time": "3:35:47"}
63
+ {"current_steps": 630, "total_steps": 1438, "loss": 1.2803, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.983037722126978e-05, "epoch": 0.88, "percentage": 43.81, "elapsed_time": "2:46:15", "remaining_time": "3:33:14"}
64
+ {"current_steps": 640, "total_steps": 1438, "loss": 1.2731, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.929338505432045e-05, "epoch": 0.89, "percentage": 44.51, "elapsed_time": "2:48:53", "remaining_time": "3:30:35"}
65
+ {"current_steps": 650, "total_steps": 1438, "loss": 1.2652, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8754343780829968e-05, "epoch": 0.9, "percentage": 45.2, "elapsed_time": "2:51:32", "remaining_time": "3:27:58"}
66
+ {"current_steps": 660, "total_steps": 1438, "loss": 1.2717, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.821351066936043e-05, "epoch": 0.92, "percentage": 45.9, "elapsed_time": "2:54:09", "remaining_time": "3:25:18"}
67
+ {"current_steps": 670, "total_steps": 1438, "loss": 1.259, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.767114384366555e-05, "epoch": 0.93, "percentage": 46.59, "elapsed_time": "2:56:52", "remaining_time": "3:22:45"}
68
+ {"current_steps": 680, "total_steps": 1438, "loss": 1.2753, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7127502159495782e-05, "epoch": 0.95, "percentage": 47.29, "elapsed_time": "2:59:28", "remaining_time": "3:20:04"}
69
+ {"current_steps": 690, "total_steps": 1438, "loss": 1.2744, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6582845081054096e-05, "epoch": 0.96, "percentage": 47.98, "elapsed_time": "3:02:08", "remaining_time": "3:17:27"}
70
+ {"current_steps": 700, "total_steps": 1438, "loss": 1.2634, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6037432557161285e-05, "epoch": 0.97, "percentage": 48.68, "elapsed_time": "3:04:50", "remaining_time": "3:14:52"}
71
+ {"current_steps": 710, "total_steps": 1438, "loss": 1.2668, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5491524897190068e-05, "epoch": 0.99, "percentage": 49.37, "elapsed_time": "3:07:31", "remaining_time": "3:12:16"}
72
+ {"current_steps": 720, "total_steps": 1438, "loss": 1.2642, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4945382646827058e-05, "epoch": 1.0, "percentage": 50.07, "elapsed_time": "3:10:05", "remaining_time": "3:09:34"}
73
+ {"current_steps": 730, "total_steps": 1438, "loss": 1.2636, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4399266463721993e-05, "epoch": 1.02, "percentage": 50.76, "elapsed_time": "3:12:38", "remaining_time": "3:06:50"}
74
+ {"current_steps": 740, "total_steps": 1438, "loss": 1.269, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3853436993083453e-05, "epoch": 1.03, "percentage": 51.46, "elapsed_time": "3:15:20", "remaining_time": "3:04:14"}
75
+ {"current_steps": 750, "total_steps": 1438, "loss": 1.2489, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3308154743280595e-05, "epoch": 1.04, "percentage": 52.16, "elapsed_time": "3:17:58", "remaining_time": "3:01:36"}
76
+ {"current_steps": 760, "total_steps": 1438, "loss": 1.2586, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2763679961510137e-05, "epoch": 1.06, "percentage": 52.85, "elapsed_time": "3:20:32", "remaining_time": "2:58:54"}
77
+ {"current_steps": 770, "total_steps": 1438, "loss": 1.2633, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.222027250958805e-05, "epoch": 1.07, "percentage": 53.55, "elapsed_time": "3:23:15", "remaining_time": "2:56:20"}
78
+ {"current_steps": 780, "total_steps": 1438, "loss": 1.2576, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1678191739925107e-05, "epoch": 1.08, "percentage": 54.24, "elapsed_time": "3:25:53", "remaining_time": "2:53:41"}
79
+ {"current_steps": 790, "total_steps": 1438, "loss": 1.259, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1137696371745608e-05, "epoch": 1.1, "percentage": 54.94, "elapsed_time": "3:28:30", "remaining_time": "2:51:02"}
80
+ {"current_steps": 800, "total_steps": 1438, "loss": 1.2697, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.059904436760835e-05, "epoch": 1.11, "percentage": 55.63, "elapsed_time": "3:31:08", "remaining_time": "2:48:23"}
81
+ {"current_steps": 810, "total_steps": 1438, "loss": 1.2505, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.006249281028859e-05, "epoch": 1.13, "percentage": 56.33, "elapsed_time": "3:33:52", "remaining_time": "2:45:49"}
82
+ {"current_steps": 820, "total_steps": 1438, "loss": 1.2651, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9528297780080067e-05, "epoch": 1.14, "percentage": 57.02, "elapsed_time": "3:36:33", "remaining_time": "2:43:12"}
83
+ {"current_steps": 830, "total_steps": 1438, "loss": 1.2569, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.899671423257534e-05, "epoch": 1.15, "percentage": 57.72, "elapsed_time": "3:39:07", "remaining_time": "2:40:30"}
84
+ {"current_steps": 840, "total_steps": 1438, "loss": 1.2617, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8467995876983002e-05, "epoch": 1.17, "percentage": 58.41, "elapsed_time": "3:41:48", "remaining_time": "2:37:54"}
85
+ {"current_steps": 850, "total_steps": 1438, "loss": 1.2501, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7942395055039756e-05, "epoch": 1.18, "percentage": 59.11, "elapsed_time": "3:44:23", "remaining_time": "2:35:13"}
86
+ {"current_steps": 860, "total_steps": 1438, "loss": 1.2575, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.742016262057507e-05, "epoch": 1.2, "percentage": 59.81, "elapsed_time": "3:47:04", "remaining_time": "2:32:36"}
87
+ {"current_steps": 870, "total_steps": 1438, "loss": 1.2583, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.690154781978604e-05, "epoch": 1.21, "percentage": 60.5, "elapsed_time": "3:49:40", "remaining_time": "2:29:57"}
88
+ {"current_steps": 880, "total_steps": 1438, "loss": 1.2671, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.638679817227951e-05, "epoch": 1.22, "percentage": 61.2, "elapsed_time": "3:52:20", "remaining_time": "2:27:19"}
89
+ {"current_steps": 890, "total_steps": 1438, "loss": 1.2547, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5876159352938202e-05, "epoch": 1.24, "percentage": 61.89, "elapsed_time": "3:54:59", "remaining_time": "2:24:41"}
90
+ {"current_steps": 900, "total_steps": 1438, "loss": 1.2585, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5369875074667365e-05, "epoch": 1.25, "percentage": 62.59, "elapsed_time": "3:57:38", "remaining_time": "2:22:03"}
91
+ {"current_steps": 910, "total_steps": 1438, "loss": 1.2496, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4868186972077708e-05, "epoch": 1.27, "percentage": 63.28, "elapsed_time": "4:00:16", "remaining_time": "2:19:25"}
92
+ {"current_steps": 920, "total_steps": 1438, "loss": 1.2524, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4371334486160354e-05, "epoch": 1.28, "percentage": 63.98, "elapsed_time": "4:02:53", "remaining_time": "2:16:45"}
93
+ {"current_steps": 930, "total_steps": 1438, "loss": 1.2605, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3879554750008653e-05, "epoch": 1.29, "percentage": 64.67, "elapsed_time": "4:05:36", "remaining_time": "2:14:09"}
94
+ {"current_steps": 940, "total_steps": 1438, "loss": 1.247, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3393082475641544e-05, "epoch": 1.31, "percentage": 65.37, "elapsed_time": "4:08:11", "remaining_time": "2:11:29"}
95
+ {"current_steps": 950, "total_steps": 1438, "loss": 1.2629, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2912149841982388e-05, "epoch": 1.32, "percentage": 66.06, "elapsed_time": "4:10:45", "remaining_time": "2:08:48"}
96
+ {"current_steps": 960, "total_steps": 1438, "loss": 1.2493, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2436986384046786e-05, "epoch": 1.34, "percentage": 66.76, "elapsed_time": "4:13:27", "remaining_time": "2:06:11"}
97
+ {"current_steps": 970, "total_steps": 1438, "loss": 1.2556, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1967818883392306e-05, "epoch": 1.35, "percentage": 67.45, "elapsed_time": "4:16:03", "remaining_time": "2:03:32"}
98
+ {"current_steps": 980, "total_steps": 1438, "loss": 1.2531, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.150487125988224e-05, "epoch": 1.36, "percentage": 68.15, "elapsed_time": "4:18:39", "remaining_time": "2:00:52"}
99
+ {"current_steps": 990, "total_steps": 1438, "loss": 1.2549, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1048364464815297e-05, "epoch": 1.38, "percentage": 68.85, "elapsed_time": "4:21:20", "remaining_time": "1:58:15"}
100
+ {"current_steps": 1000, "total_steps": 1438, "loss": 1.2554, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0598516375471978e-05, "epoch": 1.39, "percentage": 69.54, "elapsed_time": "4:23:58", "remaining_time": "1:55:37"}
101
+ {"current_steps": 1010, "total_steps": 1438, "loss": 1.247, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0155541691128212e-05, "epoch": 1.4, "percentage": 70.24, "elapsed_time": "4:26:34", "remaining_time": "1:52:57"}
102
+ {"current_steps": 1020, "total_steps": 1438, "loss": 1.2541, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.719651830585668e-06, "epoch": 1.42, "percentage": 70.93, "elapsed_time": "4:29:10", "remaining_time": "1:50:18"}
103
+ {"current_steps": 1030, "total_steps": 1438, "loss": 1.2567, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.291054831267749e-06, "epoch": 1.43, "percentage": 71.63, "elapsed_time": "4:31:52", "remaining_time": "1:47:41"}
104
+ {"current_steps": 1040, "total_steps": 1438, "loss": 1.2455, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.869955249929509e-06, "epoch": 1.45, "percentage": 72.32, "elapsed_time": "4:34:38", "remaining_time": "1:45:06"}
105
+ {"current_steps": 1050, "total_steps": 1438, "loss": 1.2525, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.456554065028651e-06, "epoch": 1.46, "percentage": 73.02, "elapsed_time": "4:37:14", "remaining_time": "1:42:26"}
106
+ {"current_steps": 1060, "total_steps": 1438, "loss": 1.2583, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.051048580804457e-06, "epoch": 1.47, "percentage": 73.71, "elapsed_time": "4:39:58", "remaining_time": "1:39:50"}
107
+ {"current_steps": 1070, "total_steps": 1438, "loss": 1.255, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.65363233311028e-06, "epoch": 1.49, "percentage": 74.41, "elapsed_time": "4:42:37", "remaining_time": "1:37:12"}
108
+ {"current_steps": 1080, "total_steps": 1438, "loss": 1.2548, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.264494997044522e-06, "epoch": 1.5, "percentage": 75.1, "elapsed_time": "4:45:18", "remaining_time": "1:34:34"}
109
+ {"current_steps": 1090, "total_steps": 1438, "loss": 1.2549, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.88382229642433e-06, "epoch": 1.52, "percentage": 75.8, "elapsed_time": "4:47:55", "remaining_time": "1:31:55"}
110
+ {"current_steps": 1100, "total_steps": 1438, "loss": 1.2577, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.51179591514505e-06, "epoch": 1.53, "percentage": 76.5, "elapsed_time": "4:50:30", "remaining_time": "1:29:15"}
111
+ {"current_steps": 1110, "total_steps": 1438, "loss": 1.2471, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.1485934104678285e-06, "epoch": 1.54, "percentage": 77.19, "elapsed_time": "4:53:02", "remaining_time": "1:26:35"}
112
+ {"current_steps": 1120, "total_steps": 1438, "loss": 1.2502, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.794388128276798e-06, "epoch": 1.56, "percentage": 77.89, "elapsed_time": "4:55:39", "remaining_time": "1:23:56"}
113
+ {"current_steps": 1130, "total_steps": 1438, "loss": 1.2581, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.449349120346137e-06, "epoch": 1.57, "percentage": 78.58, "elapsed_time": "4:58:15", "remaining_time": "1:21:17"}
114
+ {"current_steps": 1140, "total_steps": 1438, "loss": 1.252, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.113641063656618e-06, "epoch": 1.59, "percentage": 79.28, "elapsed_time": "5:00:50", "remaining_time": "1:18:38"}
115
+ {"current_steps": 1150, "total_steps": 1438, "loss": 1.2497, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.787424181800174e-06, "epoch": 1.6, "percentage": 79.97, "elapsed_time": "5:03:28", "remaining_time": "1:16:00"}
116
+ {"current_steps": 1160, "total_steps": 1438, "loss": 1.2539, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.470854168509819e-06, "epoch": 1.61, "percentage": 80.67, "elapsed_time": "5:06:13", "remaining_time": "1:13:23"}
117
+ {"current_steps": 1170, "total_steps": 1438, "loss": 1.2643, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.164082113351672e-06, "epoch": 1.63, "percentage": 81.36, "elapsed_time": "5:08:49", "remaining_time": "1:10:44"}
118
+ {"current_steps": 1180, "total_steps": 1438, "loss": 1.2448, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.867254429614281e-06, "epoch": 1.64, "percentage": 82.06, "elapsed_time": "5:11:28", "remaining_time": "1:08:06"}
119
+ {"current_steps": 1190, "total_steps": 1438, "loss": 1.2487, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.580512784429921e-06, "epoch": 1.66, "percentage": 82.75, "elapsed_time": "5:14:02", "remaining_time": "1:05:26"}
120
+ {"current_steps": 1200, "total_steps": 1438, "loss": 1.2544, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3039940311609868e-06, "epoch": 1.67, "percentage": 83.45, "elapsed_time": "5:16:39", "remaining_time": "1:02:48"}
121
+ {"current_steps": 1210, "total_steps": 1438, "loss": 1.2491, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0378301440839253e-06, "epoch": 1.68, "percentage": 84.14, "elapsed_time": "5:19:16", "remaining_time": "1:00:09"}
122
+ {"current_steps": 1220, "total_steps": 1438, "loss": 1.2545, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7821481554018065e-06, "epoch": 1.7, "percentage": 84.84, "elapsed_time": "5:21:49", "remaining_time": "0:57:30"}
123
+ {"current_steps": 1230, "total_steps": 1438, "loss": 1.2477, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5370700946155456e-06, "epoch": 1.71, "percentage": 85.54, "elapsed_time": "5:24:24", "remaining_time": "0:54:51"}
124
+ {"current_steps": 1240, "total_steps": 1438, "loss": 1.2564, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3027129302828494e-06, "epoch": 1.72, "percentage": 86.23, "elapsed_time": "5:27:06", "remaining_time": "0:52:13"}
125
+ {"current_steps": 1250, "total_steps": 1438, "loss": 1.2481, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0791885141925344e-06, "epoch": 1.74, "percentage": 86.93, "elapsed_time": "5:29:45", "remaining_time": "0:49:35"}
126
+ {"current_steps": 1260, "total_steps": 1438, "loss": 1.2476, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8666035279809535e-06, "epoch": 1.75, "percentage": 87.62, "elapsed_time": "5:32:26", "remaining_time": "0:46:57"}
127
+ {"current_steps": 1270, "total_steps": 1438, "loss": 1.2538, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6650594322160097e-06, "epoch": 1.77, "percentage": 88.32, "elapsed_time": "5:35:02", "remaining_time": "0:44:19"}
128
+ {"current_steps": 1280, "total_steps": 1438, "loss": 1.249, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4746524179729742e-06, "epoch": 1.78, "percentage": 89.01, "elapsed_time": "5:37:48", "remaining_time": "0:41:41"}
129
+ {"current_steps": 1290, "total_steps": 1438, "loss": 1.2518, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.295473360925345e-06, "epoch": 1.79, "percentage": 89.71, "elapsed_time": "5:40:22", "remaining_time": "0:39:03"}
130
+ {"current_steps": 1300, "total_steps": 1438, "loss": 1.2569, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1276077779725335e-06, "epoch": 1.81, "percentage": 90.4, "elapsed_time": "5:43:06", "remaining_time": "0:36:25"}
131
+ {"current_steps": 1310, "total_steps": 1438, "loss": 1.252, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.711357864251647e-07, "epoch": 1.82, "percentage": 91.1, "elapsed_time": "5:45:41", "remaining_time": "0:33:46"}
132
+ {"current_steps": 1320, "total_steps": 1438, "loss": 1.2554, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.261320657674626e-07, "epoch": 1.84, "percentage": 91.79, "elapsed_time": "5:48:21", "remaining_time": "0:31:08"}
133
+ {"current_steps": 1330, "total_steps": 1438, "loss": 1.2504, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.926658220148929e-07, "epoch": 1.85, "percentage": 92.49, "elapsed_time": "5:51:05", "remaining_time": "0:28:30"}
134
+ {"current_steps": 1340, "total_steps": 1438, "loss": 1.2466, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.708007546841893e-07, "epoch": 1.86, "percentage": 93.18, "elapsed_time": "5:53:42", "remaining_time": "0:25:52"}
135
+ {"current_steps": 1350, "total_steps": 1438, "loss": 1.2581, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6059502639142773e-07, "epoch": 1.88, "percentage": 93.88, "elapsed_time": "5:56:19", "remaining_time": "0:23:13"}
136
+ {"current_steps": 1360, "total_steps": 1438, "loss": 1.2511, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6210123509273775e-07, "epoch": 1.89, "percentage": 94.58, "elapsed_time": "5:59:02", "remaining_time": "0:20:35"}
137
+ {"current_steps": 1370, "total_steps": 1438, "loss": 1.2505, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.753663889808328e-07, "epoch": 1.91, "percentage": 95.27, "elapsed_time": "6:01:42", "remaining_time": "0:17:57"}
138
+ {"current_steps": 1380, "total_steps": 1438, "loss": 1.2503, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0043188404937075e-07, "epoch": 1.92, "percentage": 95.97, "elapsed_time": "6:04:20", "remaining_time": "0:15:18"}
139
+ {"current_steps": 1390, "total_steps": 1438, "loss": 1.2462, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3733348433589143e-07, "epoch": 1.93, "percentage": 96.66, "elapsed_time": "6:07:02", "remaining_time": "0:12:40"}
140
+ {"current_steps": 1400, "total_steps": 1438, "loss": 1.2578, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.610130485265655e-08, "epoch": 1.95, "percentage": 97.36, "elapsed_time": "6:09:40", "remaining_time": "0:10:02"}
141
+ {"current_steps": 1410, "total_steps": 1438, "loss": 1.2563, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.67597972136663e-08, "epoch": 1.96, "percentage": 98.05, "elapsed_time": "6:12:24", "remaining_time": "0:07:23"}
142
+ {"current_steps": 1420, "total_steps": 1438, "loss": 1.2589, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9327737964616733e-08, "epoch": 1.97, "percentage": 98.75, "elapsed_time": "6:15:00", "remaining_time": "0:04:45"}
143
+ {"current_steps": 1430, "total_steps": 1438, "loss": 1.2553, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.8182196213903955e-09, "epoch": 1.99, "percentage": 99.44, "elapsed_time": "6:17:40", "remaining_time": "0:02:06"}
144
+ {"current_steps": 1438, "total_steps": 1438, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "6:19:50", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,883 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 1438,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 4.999403411726636e-05,
13
+ "loss": 1.8493,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.03,
18
+ "learning_rate": 4.997613931640598e-05,
19
+ "loss": 1.613,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.04,
24
+ "learning_rate": 4.9946324138081534e-05,
25
+ "loss": 1.5193,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.06,
30
+ "learning_rate": 4.990460281220164e-05,
31
+ "loss": 1.4805,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.07,
36
+ "learning_rate": 4.98509952511293e-05,
37
+ "loss": 1.443,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.08,
42
+ "learning_rate": 4.978552704017835e-05,
43
+ "loss": 1.4186,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.1,
48
+ "learning_rate": 4.9708229425402354e-05,
49
+ "loss": 1.394,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.11,
54
+ "learning_rate": 4.961913929868172e-05,
55
+ "loss": 1.38,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.13,
60
+ "learning_rate": 4.9518299180116366e-05,
61
+ "loss": 1.3715,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.14,
66
+ "learning_rate": 4.940575719773205e-05,
67
+ "loss": 1.3548,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.15,
72
+ "learning_rate": 4.928156706451035e-05,
73
+ "loss": 1.3536,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.17,
78
+ "learning_rate": 4.9145788052752975e-05,
79
+ "loss": 1.3535,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.18,
84
+ "learning_rate": 4.899848496579287e-05,
85
+ "loss": 1.3414,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.19,
90
+ "learning_rate": 4.883972810706548e-05,
91
+ "loss": 1.3275,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.21,
96
+ "learning_rate": 4.866959324655501e-05,
97
+ "loss": 1.3342,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.22,
102
+ "learning_rate": 4.8488161584631574e-05,
103
+ "loss": 1.3234,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.24,
108
+ "learning_rate": 4.829551971329672e-05,
109
+ "loss": 1.3235,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 0.25,
114
+ "learning_rate": 4.809175957485558e-05,
115
+ "loss": 1.3245,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 0.26,
120
+ "learning_rate": 4.7876978418035455e-05,
121
+ "loss": 1.3132,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 0.28,
126
+ "learning_rate": 4.7651278751571984e-05,
127
+ "loss": 1.3193,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 0.29,
132
+ "learning_rate": 4.7414768295284594e-05,
133
+ "loss": 1.3158,
134
+ "step": 210
135
+ },
136
+ {
137
+ "epoch": 0.31,
138
+ "learning_rate": 4.716755992866509e-05,
139
+ "loss": 1.3089,
140
+ "step": 220
141
+ },
142
+ {
143
+ "epoch": 0.32,
144
+ "learning_rate": 4.6909771637003556e-05,
145
+ "loss": 1.3232,
146
+ "step": 230
147
+ },
148
+ {
149
+ "epoch": 0.33,
150
+ "learning_rate": 4.664152645507744e-05,
151
+ "loss": 1.307,
152
+ "step": 240
153
+ },
154
+ {
155
+ "epoch": 0.35,
156
+ "learning_rate": 4.636295240843068e-05,
157
+ "loss": 1.3057,
158
+ "step": 250
159
+ },
160
+ {
161
+ "epoch": 0.36,
162
+ "learning_rate": 4.607418245227089e-05,
163
+ "loss": 1.2985,
164
+ "step": 260
165
+ },
166
+ {
167
+ "epoch": 0.38,
168
+ "learning_rate": 4.577535440801368e-05,
169
+ "loss": 1.3111,
170
+ "step": 270
171
+ },
172
+ {
173
+ "epoch": 0.39,
174
+ "learning_rate": 4.546661089750462e-05,
175
+ "loss": 1.2948,
176
+ "step": 280
177
+ },
178
+ {
179
+ "epoch": 0.4,
180
+ "learning_rate": 4.5148099274950005e-05,
181
+ "loss": 1.3037,
182
+ "step": 290
183
+ },
184
+ {
185
+ "epoch": 0.42,
186
+ "learning_rate": 4.481997155658898e-05,
187
+ "loss": 1.3042,
188
+ "step": 300
189
+ },
190
+ {
191
+ "epoch": 0.43,
192
+ "learning_rate": 4.4482384348140695e-05,
193
+ "loss": 1.2899,
194
+ "step": 310
195
+ },
196
+ {
197
+ "epoch": 0.45,
198
+ "learning_rate": 4.413549877006099e-05,
199
+ "loss": 1.3006,
200
+ "step": 320
201
+ },
202
+ {
203
+ "epoch": 0.46,
204
+ "learning_rate": 4.3779480380644337e-05,
205
+ "loss": 1.2908,
206
+ "step": 330
207
+ },
208
+ {
209
+ "epoch": 0.47,
210
+ "learning_rate": 4.34144990970077e-05,
211
+ "loss": 1.2898,
212
+ "step": 340
213
+ },
214
+ {
215
+ "epoch": 0.49,
216
+ "learning_rate": 4.304072911399415e-05,
217
+ "loss": 1.2822,
218
+ "step": 350
219
+ },
220
+ {
221
+ "epoch": 0.5,
222
+ "learning_rate": 4.2658348821034724e-05,
223
+ "loss": 1.2927,
224
+ "step": 360
225
+ },
226
+ {
227
+ "epoch": 0.51,
228
+ "learning_rate": 4.226754071700841e-05,
229
+ "loss": 1.2847,
230
+ "step": 370
231
+ },
232
+ {
233
+ "epoch": 0.53,
234
+ "learning_rate": 4.1868491323140816e-05,
235
+ "loss": 1.2873,
236
+ "step": 380
237
+ },
238
+ {
239
+ "epoch": 0.54,
240
+ "learning_rate": 4.146139109398303e-05,
241
+ "loss": 1.288,
242
+ "step": 390
243
+ },
244
+ {
245
+ "epoch": 0.56,
246
+ "learning_rate": 4.1046434326513305e-05,
247
+ "loss": 1.2849,
248
+ "step": 400
249
+ },
250
+ {
251
+ "epoch": 0.57,
252
+ "learning_rate": 4.062381906740477e-05,
253
+ "loss": 1.2819,
254
+ "step": 410
255
+ },
256
+ {
257
+ "epoch": 0.58,
258
+ "learning_rate": 4.019374701850362e-05,
259
+ "loss": 1.2694,
260
+ "step": 420
261
+ },
262
+ {
263
+ "epoch": 0.6,
264
+ "learning_rate": 3.975642344056271e-05,
265
+ "loss": 1.2843,
266
+ "step": 430
267
+ },
268
+ {
269
+ "epoch": 0.61,
270
+ "learning_rate": 3.931205705527664e-05,
271
+ "loss": 1.2646,
272
+ "step": 440
273
+ },
274
+ {
275
+ "epoch": 0.63,
276
+ "learning_rate": 3.886085994566506e-05,
277
+ "loss": 1.277,
278
+ "step": 450
279
+ },
280
+ {
281
+ "epoch": 0.64,
282
+ "learning_rate": 3.840304745485162e-05,
283
+ "loss": 1.2769,
284
+ "step": 460
285
+ },
286
+ {
287
+ "epoch": 0.65,
288
+ "learning_rate": 3.7938838083287056e-05,
289
+ "loss": 1.2797,
290
+ "step": 470
291
+ },
292
+ {
293
+ "epoch": 0.67,
294
+ "learning_rate": 3.746845338446533e-05,
295
+ "loss": 1.2776,
296
+ "step": 480
297
+ },
298
+ {
299
+ "epoch": 0.68,
300
+ "learning_rate": 3.6992117859182674e-05,
301
+ "loss": 1.2847,
302
+ "step": 490
303
+ },
304
+ {
305
+ "epoch": 0.7,
306
+ "learning_rate": 3.651005884838995e-05,
307
+ "loss": 1.2762,
308
+ "step": 500
309
+ },
310
+ {
311
+ "epoch": 0.71,
312
+ "learning_rate": 3.6022506424689485e-05,
313
+ "loss": 1.2834,
314
+ "step": 510
315
+ },
316
+ {
317
+ "epoch": 0.72,
318
+ "learning_rate": 3.552969328252817e-05,
319
+ "loss": 1.2754,
320
+ "step": 520
321
+ },
322
+ {
323
+ "epoch": 0.74,
324
+ "learning_rate": 3.5031854627139284e-05,
325
+ "loss": 1.2807,
326
+ "step": 530
327
+ },
328
+ {
329
+ "epoch": 0.75,
330
+ "learning_rate": 3.452922806228587e-05,
331
+ "loss": 1.2783,
332
+ "step": 540
333
+ },
334
+ {
335
+ "epoch": 0.76,
336
+ "learning_rate": 3.402205347685953e-05,
337
+ "loss": 1.2748,
338
+ "step": 550
339
+ },
340
+ {
341
+ "epoch": 0.78,
342
+ "learning_rate": 3.351057293038841e-05,
343
+ "loss": 1.2737,
344
+ "step": 560
345
+ },
346
+ {
347
+ "epoch": 0.79,
348
+ "learning_rate": 3.2995030537509396e-05,
349
+ "loss": 1.2729,
350
+ "step": 570
351
+ },
352
+ {
353
+ "epoch": 0.81,
354
+ "learning_rate": 3.247567235145929e-05,
355
+ "loss": 1.2712,
356
+ "step": 580
357
+ },
358
+ {
359
+ "epoch": 0.82,
360
+ "learning_rate": 3.195274624664086e-05,
361
+ "loss": 1.2716,
362
+ "step": 590
363
+ },
364
+ {
365
+ "epoch": 0.83,
366
+ "learning_rate": 3.14265018003197e-05,
367
+ "loss": 1.2823,
368
+ "step": 600
369
+ },
370
+ {
371
+ "epoch": 0.85,
372
+ "learning_rate": 3.089719017350828e-05,
373
+ "loss": 1.2627,
374
+ "step": 610
375
+ },
376
+ {
377
+ "epoch": 0.86,
378
+ "learning_rate": 3.03650639910942e-05,
379
+ "loss": 1.2658,
380
+ "step": 620
381
+ },
382
+ {
383
+ "epoch": 0.88,
384
+ "learning_rate": 2.983037722126978e-05,
385
+ "loss": 1.2803,
386
+ "step": 630
387
+ },
388
+ {
389
+ "epoch": 0.89,
390
+ "learning_rate": 2.929338505432045e-05,
391
+ "loss": 1.2731,
392
+ "step": 640
393
+ },
394
+ {
395
+ "epoch": 0.9,
396
+ "learning_rate": 2.8754343780829968e-05,
397
+ "loss": 1.2652,
398
+ "step": 650
399
+ },
400
+ {
401
+ "epoch": 0.92,
402
+ "learning_rate": 2.821351066936043e-05,
403
+ "loss": 1.2717,
404
+ "step": 660
405
+ },
406
+ {
407
+ "epoch": 0.93,
408
+ "learning_rate": 2.767114384366555e-05,
409
+ "loss": 1.259,
410
+ "step": 670
411
+ },
412
+ {
413
+ "epoch": 0.95,
414
+ "learning_rate": 2.7127502159495782e-05,
415
+ "loss": 1.2753,
416
+ "step": 680
417
+ },
418
+ {
419
+ "epoch": 0.96,
420
+ "learning_rate": 2.6582845081054096e-05,
421
+ "loss": 1.2744,
422
+ "step": 690
423
+ },
424
+ {
425
+ "epoch": 0.97,
426
+ "learning_rate": 2.6037432557161285e-05,
427
+ "loss": 1.2634,
428
+ "step": 700
429
+ },
430
+ {
431
+ "epoch": 0.99,
432
+ "learning_rate": 2.5491524897190068e-05,
433
+ "loss": 1.2668,
434
+ "step": 710
435
+ },
436
+ {
437
+ "epoch": 1.0,
438
+ "learning_rate": 2.4945382646827058e-05,
439
+ "loss": 1.2642,
440
+ "step": 720
441
+ },
442
+ {
443
+ "epoch": 1.02,
444
+ "learning_rate": 2.4399266463721993e-05,
445
+ "loss": 1.2636,
446
+ "step": 730
447
+ },
448
+ {
449
+ "epoch": 1.03,
450
+ "learning_rate": 2.3853436993083453e-05,
451
+ "loss": 1.269,
452
+ "step": 740
453
+ },
454
+ {
455
+ "epoch": 1.04,
456
+ "learning_rate": 2.3308154743280595e-05,
457
+ "loss": 1.2489,
458
+ "step": 750
459
+ },
460
+ {
461
+ "epoch": 1.06,
462
+ "learning_rate": 2.2763679961510137e-05,
463
+ "loss": 1.2586,
464
+ "step": 760
465
+ },
466
+ {
467
+ "epoch": 1.07,
468
+ "learning_rate": 2.222027250958805e-05,
469
+ "loss": 1.2633,
470
+ "step": 770
471
+ },
472
+ {
473
+ "epoch": 1.08,
474
+ "learning_rate": 2.1678191739925107e-05,
475
+ "loss": 1.2576,
476
+ "step": 780
477
+ },
478
+ {
479
+ "epoch": 1.1,
480
+ "learning_rate": 2.1137696371745608e-05,
481
+ "loss": 1.259,
482
+ "step": 790
483
+ },
484
+ {
485
+ "epoch": 1.11,
486
+ "learning_rate": 2.059904436760835e-05,
487
+ "loss": 1.2697,
488
+ "step": 800
489
+ },
490
+ {
491
+ "epoch": 1.13,
492
+ "learning_rate": 2.006249281028859e-05,
493
+ "loss": 1.2505,
494
+ "step": 810
495
+ },
496
+ {
497
+ "epoch": 1.14,
498
+ "learning_rate": 1.9528297780080067e-05,
499
+ "loss": 1.2651,
500
+ "step": 820
501
+ },
502
+ {
503
+ "epoch": 1.15,
504
+ "learning_rate": 1.899671423257534e-05,
505
+ "loss": 1.2569,
506
+ "step": 830
507
+ },
508
+ {
509
+ "epoch": 1.17,
510
+ "learning_rate": 1.8467995876983002e-05,
511
+ "loss": 1.2617,
512
+ "step": 840
513
+ },
514
+ {
515
+ "epoch": 1.18,
516
+ "learning_rate": 1.7942395055039756e-05,
517
+ "loss": 1.2501,
518
+ "step": 850
519
+ },
520
+ {
521
+ "epoch": 1.2,
522
+ "learning_rate": 1.742016262057507e-05,
523
+ "loss": 1.2575,
524
+ "step": 860
525
+ },
526
+ {
527
+ "epoch": 1.21,
528
+ "learning_rate": 1.690154781978604e-05,
529
+ "loss": 1.2583,
530
+ "step": 870
531
+ },
532
+ {
533
+ "epoch": 1.22,
534
+ "learning_rate": 1.638679817227951e-05,
535
+ "loss": 1.2671,
536
+ "step": 880
537
+ },
538
+ {
539
+ "epoch": 1.24,
540
+ "learning_rate": 1.5876159352938202e-05,
541
+ "loss": 1.2547,
542
+ "step": 890
543
+ },
544
+ {
545
+ "epoch": 1.25,
546
+ "learning_rate": 1.5369875074667365e-05,
547
+ "loss": 1.2585,
548
+ "step": 900
549
+ },
550
+ {
551
+ "epoch": 1.27,
552
+ "learning_rate": 1.4868186972077708e-05,
553
+ "loss": 1.2496,
554
+ "step": 910
555
+ },
556
+ {
557
+ "epoch": 1.28,
558
+ "learning_rate": 1.4371334486160354e-05,
559
+ "loss": 1.2524,
560
+ "step": 920
561
+ },
562
+ {
563
+ "epoch": 1.29,
564
+ "learning_rate": 1.3879554750008653e-05,
565
+ "loss": 1.2605,
566
+ "step": 930
567
+ },
568
+ {
569
+ "epoch": 1.31,
570
+ "learning_rate": 1.3393082475641544e-05,
571
+ "loss": 1.247,
572
+ "step": 940
573
+ },
574
+ {
575
+ "epoch": 1.32,
576
+ "learning_rate": 1.2912149841982388e-05,
577
+ "loss": 1.2629,
578
+ "step": 950
579
+ },
580
+ {
581
+ "epoch": 1.34,
582
+ "learning_rate": 1.2436986384046786e-05,
583
+ "loss": 1.2493,
584
+ "step": 960
585
+ },
586
+ {
587
+ "epoch": 1.35,
588
+ "learning_rate": 1.1967818883392306e-05,
589
+ "loss": 1.2556,
590
+ "step": 970
591
+ },
592
+ {
593
+ "epoch": 1.36,
594
+ "learning_rate": 1.150487125988224e-05,
595
+ "loss": 1.2531,
596
+ "step": 980
597
+ },
598
+ {
599
+ "epoch": 1.38,
600
+ "learning_rate": 1.1048364464815297e-05,
601
+ "loss": 1.2549,
602
+ "step": 990
603
+ },
604
+ {
605
+ "epoch": 1.39,
606
+ "learning_rate": 1.0598516375471978e-05,
607
+ "loss": 1.2554,
608
+ "step": 1000
609
+ },
610
+ {
611
+ "epoch": 1.4,
612
+ "learning_rate": 1.0155541691128212e-05,
613
+ "loss": 1.247,
614
+ "step": 1010
615
+ },
616
+ {
617
+ "epoch": 1.42,
618
+ "learning_rate": 9.719651830585668e-06,
619
+ "loss": 1.2541,
620
+ "step": 1020
621
+ },
622
+ {
623
+ "epoch": 1.43,
624
+ "learning_rate": 9.291054831267749e-06,
625
+ "loss": 1.2567,
626
+ "step": 1030
627
+ },
628
+ {
629
+ "epoch": 1.45,
630
+ "learning_rate": 8.869955249929509e-06,
631
+ "loss": 1.2455,
632
+ "step": 1040
633
+ },
634
+ {
635
+ "epoch": 1.46,
636
+ "learning_rate": 8.456554065028651e-06,
637
+ "loss": 1.2525,
638
+ "step": 1050
639
+ },
640
+ {
641
+ "epoch": 1.47,
642
+ "learning_rate": 8.051048580804457e-06,
643
+ "loss": 1.2583,
644
+ "step": 1060
645
+ },
646
+ {
647
+ "epoch": 1.49,
648
+ "learning_rate": 7.65363233311028e-06,
649
+ "loss": 1.255,
650
+ "step": 1070
651
+ },
652
+ {
653
+ "epoch": 1.5,
654
+ "learning_rate": 7.264494997044522e-06,
655
+ "loss": 1.2548,
656
+ "step": 1080
657
+ },
658
+ {
659
+ "epoch": 1.52,
660
+ "learning_rate": 6.88382229642433e-06,
661
+ "loss": 1.2549,
662
+ "step": 1090
663
+ },
664
+ {
665
+ "epoch": 1.53,
666
+ "learning_rate": 6.51179591514505e-06,
667
+ "loss": 1.2577,
668
+ "step": 1100
669
+ },
670
+ {
671
+ "epoch": 1.54,
672
+ "learning_rate": 6.1485934104678285e-06,
673
+ "loss": 1.2471,
674
+ "step": 1110
675
+ },
676
+ {
677
+ "epoch": 1.56,
678
+ "learning_rate": 5.794388128276798e-06,
679
+ "loss": 1.2502,
680
+ "step": 1120
681
+ },
682
+ {
683
+ "epoch": 1.57,
684
+ "learning_rate": 5.449349120346137e-06,
685
+ "loss": 1.2581,
686
+ "step": 1130
687
+ },
688
+ {
689
+ "epoch": 1.59,
690
+ "learning_rate": 5.113641063656618e-06,
691
+ "loss": 1.252,
692
+ "step": 1140
693
+ },
694
+ {
695
+ "epoch": 1.6,
696
+ "learning_rate": 4.787424181800174e-06,
697
+ "loss": 1.2497,
698
+ "step": 1150
699
+ },
700
+ {
701
+ "epoch": 1.61,
702
+ "learning_rate": 4.470854168509819e-06,
703
+ "loss": 1.2539,
704
+ "step": 1160
705
+ },
706
+ {
707
+ "epoch": 1.63,
708
+ "learning_rate": 4.164082113351672e-06,
709
+ "loss": 1.2643,
710
+ "step": 1170
711
+ },
712
+ {
713
+ "epoch": 1.64,
714
+ "learning_rate": 3.867254429614281e-06,
715
+ "loss": 1.2448,
716
+ "step": 1180
717
+ },
718
+ {
719
+ "epoch": 1.66,
720
+ "learning_rate": 3.580512784429921e-06,
721
+ "loss": 1.2487,
722
+ "step": 1190
723
+ },
724
+ {
725
+ "epoch": 1.67,
726
+ "learning_rate": 3.3039940311609868e-06,
727
+ "loss": 1.2544,
728
+ "step": 1200
729
+ },
730
+ {
731
+ "epoch": 1.68,
732
+ "learning_rate": 3.0378301440839253e-06,
733
+ "loss": 1.2491,
734
+ "step": 1210
735
+ },
736
+ {
737
+ "epoch": 1.7,
738
+ "learning_rate": 2.7821481554018065e-06,
739
+ "loss": 1.2545,
740
+ "step": 1220
741
+ },
742
+ {
743
+ "epoch": 1.71,
744
+ "learning_rate": 2.5370700946155456e-06,
745
+ "loss": 1.2477,
746
+ "step": 1230
747
+ },
748
+ {
749
+ "epoch": 1.72,
750
+ "learning_rate": 2.3027129302828494e-06,
751
+ "loss": 1.2564,
752
+ "step": 1240
753
+ },
754
+ {
755
+ "epoch": 1.74,
756
+ "learning_rate": 2.0791885141925344e-06,
757
+ "loss": 1.2481,
758
+ "step": 1250
759
+ },
760
+ {
761
+ "epoch": 1.75,
762
+ "learning_rate": 1.8666035279809535e-06,
763
+ "loss": 1.2476,
764
+ "step": 1260
765
+ },
766
+ {
767
+ "epoch": 1.77,
768
+ "learning_rate": 1.6650594322160097e-06,
769
+ "loss": 1.2538,
770
+ "step": 1270
771
+ },
772
+ {
773
+ "epoch": 1.78,
774
+ "learning_rate": 1.4746524179729742e-06,
775
+ "loss": 1.249,
776
+ "step": 1280
777
+ },
778
+ {
779
+ "epoch": 1.79,
780
+ "learning_rate": 1.295473360925345e-06,
781
+ "loss": 1.2518,
782
+ "step": 1290
783
+ },
784
+ {
785
+ "epoch": 1.81,
786
+ "learning_rate": 1.1276077779725335e-06,
787
+ "loss": 1.2569,
788
+ "step": 1300
789
+ },
790
+ {
791
+ "epoch": 1.82,
792
+ "learning_rate": 9.711357864251647e-07,
793
+ "loss": 1.252,
794
+ "step": 1310
795
+ },
796
+ {
797
+ "epoch": 1.84,
798
+ "learning_rate": 8.261320657674626e-07,
799
+ "loss": 1.2554,
800
+ "step": 1320
801
+ },
802
+ {
803
+ "epoch": 1.85,
804
+ "learning_rate": 6.926658220148929e-07,
805
+ "loss": 1.2504,
806
+ "step": 1330
807
+ },
808
+ {
809
+ "epoch": 1.86,
810
+ "learning_rate": 5.708007546841893e-07,
811
+ "loss": 1.2466,
812
+ "step": 1340
813
+ },
814
+ {
815
+ "epoch": 1.88,
816
+ "learning_rate": 4.6059502639142773e-07,
817
+ "loss": 1.2581,
818
+ "step": 1350
819
+ },
820
+ {
821
+ "epoch": 1.89,
822
+ "learning_rate": 3.6210123509273775e-07,
823
+ "loss": 1.2511,
824
+ "step": 1360
825
+ },
826
+ {
827
+ "epoch": 1.91,
828
+ "learning_rate": 2.753663889808328e-07,
829
+ "loss": 1.2505,
830
+ "step": 1370
831
+ },
832
+ {
833
+ "epoch": 1.92,
834
+ "learning_rate": 2.0043188404937075e-07,
835
+ "loss": 1.2503,
836
+ "step": 1380
837
+ },
838
+ {
839
+ "epoch": 1.93,
840
+ "learning_rate": 1.3733348433589143e-07,
841
+ "loss": 1.2462,
842
+ "step": 1390
843
+ },
844
+ {
845
+ "epoch": 1.95,
846
+ "learning_rate": 8.610130485265655e-08,
847
+ "loss": 1.2578,
848
+ "step": 1400
849
+ },
850
+ {
851
+ "epoch": 1.96,
852
+ "learning_rate": 4.67597972136663e-08,
853
+ "loss": 1.2563,
854
+ "step": 1410
855
+ },
856
+ {
857
+ "epoch": 1.97,
858
+ "learning_rate": 1.9327737964616733e-08,
859
+ "loss": 1.2589,
860
+ "step": 1420
861
+ },
862
+ {
863
+ "epoch": 1.99,
864
+ "learning_rate": 3.8182196213903955e-09,
865
+ "loss": 1.2553,
866
+ "step": 1430
867
+ },
868
+ {
869
+ "epoch": 2.0,
870
+ "step": 1438,
871
+ "total_flos": 3.15739188563542e+18,
872
+ "train_loss": 1.285984360292989,
873
+ "train_runtime": 22790.2039,
874
+ "train_samples_per_second": 6.057,
875
+ "train_steps_per_second": 0.063
876
+ }
877
+ ],
878
+ "max_steps": 1438,
879
+ "num_train_epochs": 2,
880
+ "total_flos": 3.15739188563542e+18,
881
+ "trial_name": null,
882
+ "trial_params": null
883
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50e1ef6c01b86ac38d5b495482e7d846564796979962b6b17f1f136a64b951a3
3
+ size 3286
training_loss.png ADDED